SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.06161 · 2023

Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2310.06161.json · badge: /api/ran/2310.06161.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
estija/cmid canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
FunctionStatusWhere it lives
acc_and_f1 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
estija/cmid/utils_glue.py
pointer only (licence: MIT); the stored copy get_code serves, from danrsc/bert_brain_neurips_2019, is pointer only (licence: NONE) · get_code("cac113ca87b9d9f3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from danrsc/bert_brain_neurips_2019, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
estija/cmid/utils.py
code served (permissive licence) · get_code("621de5dd9c62c06d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small batch of output logits (batch_size=2, num_classes=4)
output = torch.randn(2, 4)

# Create small batch of target labels (batch_size=2)
target = torch.tensor([1, 3])

# Define topk parameter
topk = (1,)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
convert_examples_to_features Ran
ran; our contract draft was wrong, not the code
estija/cmid/utils_glue.py
code served (permissive licence) · get_code("c4c16e96906f44c1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import logging

logging.basicConfig(level=logging.INFO)

class SimpleTokenizer:
    """Mock tokenizer for testing."""
    def __init__(self):
        self.vocab = {
            '[CLS]': 101,
            '[SEP]': 102,
            '[PAD]': 0,
            'hello': 1,
            'world': 2,
            'this': 3,
            'is': 4,
            'a': 5,
            'test': 6,
            'example': 7,
            'text': 8,
            'good': 9,
            'bad': 10,
        }
    
    def tokenize(self, text):
        """Tokenize text into tokens."""
        return text.lower().split()
    
    def convert_tokens_to_ids(self, tokens):
        """Convert tokens to IDs."""
        return [self.vocab.get(token, 1) for token in tokens]


class Example:
    """Simple example class."""
    def __init__(self, guid, text_a, text_b, label):
        self.guid = guid
        self.text_a = text_a
        self.text_b = text_b
        self.label = label


# Create simple examples
examples = [
    Example('1', 'hello world', 'this is test', 'good'),
    Example('2', 'example text', None, 'bad'),
]

# Create label list
label_list = ['good', 'bad']

# Create tokenizer
tokenizer = SimpleTokenizer()

# Set up ARGS
ARGS = {
    'examples': examples,
    'label_list': label_list,
    'max_seq_length': 32,
    'tokenizer': tokenizer,
    'output_mode': 'classification',
    'cls_token_at_end': False,
    'cls_token': '[CLS]',
    'cls_token_segment_id': 0,
    'sep_token': '[SEP]',
    'sep_token_extra': False,
    'pad_on_left': False,
    'pad_token': 0,
    'pad_token_segment_id': 0,
    'sequence_a_segment_id': 0,
    'sequence_b_segment_id': 1,
    'mask_padding_with_zero': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_accs_for_epoch_across_batches Ran
ran; our contract draft was wrong, not the code
estija/cmid/analysis_utils.py
code served (permissive licence) · get_code("381380e09fd105f8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import pandas as pd

# Create a small DataFrame that matches the expected structure
# The function expects:
# - 'epoch' column
# - 'avg_acc_group:{group}' columns for each group
# - 'processed_data_count_group:{group}' columns for each group

n_groups = 3
n_rows = 4

data = {
    'epoch': [1, 1, 1, 2],
}

# Add accuracy and count columns for each group
for group in range(n_groups):
    data[f'avg_acc_group:{group}'] = np.random.rand(n_rows)
    data[f'processed_data_count_group:{group}'] = np.random.randint(10, 50, n_rows)

df = pd.DataFrame(data)

ARGS = {
    'df': df,
    'epoch': 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_balanced_data Ran
ran; our contract draft was wrong, not the code
estija/cmid/utils.py
code served (permissive licence) · get_code("d6fd8295f565dec5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct train_data as a list of tuples
# Each tuple contains elements where index `dim` holds a class label (0, 1, 2, or 3)
# We need enough samples of each class for balancing

train_data = []

# Create samples with label 0 at dimension 1
for i in range(100):
    train_data.append((np.array([1.0, 2.0, 3.0]), 0, 5))

# Create samples with label 1 at dimension 1
for i in range(100):
    train_data.append((np.array([4.0, 5.0, 6.0]), 1, 7))

# Create samples with label 2 at dimension 1
for i in range(50):
    train_data.append((np.array([7.0, 8.0, 9.0]), 2, 9))

# Create samples with label 3 at dimension 1
for i in range(50):
    train_data.append((np.array([10.0, 11.0, 12.0]), 3, 11))

ARGS = {
    'train_data': train_data,
    'dim': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_balanced_data_gen Ran
ran; our contract draft was wrong, not the code
estija/cmid/utils.py
code served (permissive licence) · get_code("3c6b0889ccefaeda")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Create a small stand-in class for args with a model attribute
class Args:
    def __init__(self, model_name):
        self.model = model_name

# Create train_data as a list of tuples
# Each tuple contains: (tensor data, label, optional third element)
# For non-bert model: (x, y, z)
# For bert model: (x, y, z) where x is 2D tensor with first column extracted

torch.manual_seed(0)

# Create sample data with distinct dimensions
# Each sample is a tuple of (data_tensor, class_label, auxiliary_info)
train_data = [
    (torch.randn(5, 4), 0, "aux0"),  # class 0
    (torch.randn(5, 4), 0, "aux1"),  # class 0
    (torch.randn(5, 4), 0, "aux2"),  # class 0
    (torch.randn(5, 4), 1, "aux3"),  # class 1
    (torch.randn(5, 4), 1, "aux4"),  # class 1
    (torch.randn(5, 4), 2, "aux5"),  # class 2
]

# Create args object for non-bert model
args_obj = Args("linear")

ARGS = {
    "train_data": train_data,
    "dim": 1,
    "args": args_obj
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
getbinvals Ran
ran; our contract draft was wrong, not the code
estija/cmid/cmi.py
code served (permissive licence) · get_code("f605c61af29ad962")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Analyze the function usage:
# - M: appears to be overwritten, so just needs to exist as a tensor
# - cen_arr: indexed with [i] for i in range(4), so needs 4 elements
# - Xv: passed to kernel_val, should be a scalar tensor
# - Yv: passed to kernel_val, should be a scalar tensor
# - device: used in .to(device), should be a torch device
# - sig: default 0.05, used as a float in kernel_val

device = torch.device('cpu')

# Create cen_arr with 4 elements
cen_arr = torch.tensor([0.1, 0.3, 0.5, 0.7])

# Create scalar tensors for Xv and Yv
Xv = torch.tensor(0.25)
Yv = torch.tensor(0.75)

# Create M as a small tensor (will be overwritten by the function)
M = torch.zeros(4, 4).to(device)

ARGS = {
    'M': M,
    'cen_arr': cen_arr,
    'Xv': Xv,
    'Yv': Yv,
    'device': device,
    'sig': 0.05
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (4, 4) — shape (4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
kernel_val Ran
ran; our contract draft was wrong, not the code
estija/cmid/cmi.py
code served (permissive licence) · get_code("b2d727e185d69fb0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# kernel_val takes three parameters: x, mu, and sig
# x: a tensor (the input value)
# mu: a tensor (the mean)
# sig: a scalar or tensor (the standard deviation)

x = torch.randn(2, 4)
mu = torch.randn(2, 4)
sig = 1.5

ARGS = {
    "x": x,
    "mu": mu,
    "sig": sig
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sanitize_df Ran
ran; our contract draft was wrong, not the code
estija/cmid/analysis_utils.py
code served (permissive licence) · get_code("8a66892616008c7f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataFrame. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pandas as pd
import numpy as np

# Create a valid DataFrame with epoch and batch columns
# The function expects a df with at least 'epoch' and 'batch' columns
data = {
    'epoch': [0, 0, 0, 1, 1, 1, 2, 2],
    'batch': [0, 1, 2, 0, 1, 2, 0, 1],
    'loss': [0.5, 0.4, 0.3, 0.25, 0.2, 0.15, 0.1, 0.05]
}
df = pd.DataFrame(data)

ARGS = {
    'df': df
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
validate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
estija/cmid/camelyon/camelyon.py
code served (permissive licence) · get_code("d97abd07bae67ef4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that satisfies how it's used in the function
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(3, 5)  # outputs 5 classes for argmax
    
    def forward(self, x):
        return self.linear(x)

# Build a minimal dataset class with eval method
class MinimalDataset:
    def eval(self, y_pred, y_true, metadata):
        # Just return a dummy result
        return {"accuracy": 0.5}

# Build validation loader as a list of batches
# Each batch is (x, y, metadata)
val_loader = [
    (
        torch.randn(2, 3),           # x: batch_size=2, features=3
        torch.tensor([0, 1]),         # y: batch_size=2, class labels
        torch.randn(2, 4)             # metadata: batch_size=2, metadata_dim=4
    ),
    (
        torch.randn(2, 3),
        torch.tensor([1, 0]),
        torch.randn(2, 4)
    )
]

model = MinimalModel()

# Minimal criterion (not used in the function body but required)
criterion = nn.CrossEntropyLoss()

dataset = MinimalDataset()

ARGS = {
    "val_loader": val_loader,
    "model": model,
    "criterion": criterion,
    "dataset": dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
combine_and_mask Not yet run
unverified (harvested, no recorded run)
estija/cmid/dataset_scripts/dataset_utils.py
code served (permissive licence) · get_code("fe49a67591e2b166")
How it ran

no invocation recorded.

crop_and_resize Not yet run
unverified (harvested, no recorded run)
estija/cmid/dataset_scripts/dataset_utils.py
code served (permissive licence) · get_code("e2f8b1a98dec9723")
How it ran

no invocation recorded.

est_IMYL Not yet run
unverified (harvested, no recorded run)
estija/cmid/cmi.py
code served (permissive licence) · get_code("8c45aa24af923432")
How it ran

no invocation recorded.

load_log Not yet run
unverified (harvested, no recorded run)
estija/cmid/analysis_utils.py
code served (permissive licence) · get_code("10e220982fed5f01")
How it ran

no invocation recorded.

simple_accuracy Not yet run
unverified (harvested, no recorded run)
estija/cmid/utils_glue.py
code served (permissive licence) · get_code("3c241ecfe3749a6d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 9 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
simple_accuracy 59 other papers
49 dated earlier, 2 the same month, 5 later, 3 same year, order not determinable
1506.05865 (2015-06)
LCSTS: A Large Scale Chinese Short Text Summarization Dataset
1509.01626 (2015-09)
Character-level Convolutional Networks for Text Classification *
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 56 more not named here
acc_and_f1 22 other papers
18 dated earlier, 2 later, 2 same year, order not determinable
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1905.12866 (2019-05)
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
and 19 more not named here
accuracy 6 other papers
3 dated earlier, 3 later
2302.02931 (2023-02)
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
2306.11074 (2023-06)
Simple and Fast Group Robustness by Automatic Feature Reweighting
2309.06717 (2023-09)
Bias Amplification Enhances Minority Group Performance
and 3 more not named here
convert_examples_to_features 5 other papers
3 dated earlier, 2 later
2010.10418 (2020-10)
CONJNLI: Natural Language Inference Over Conjunctive Sentences
2306.11074 (2023-06)
Simple and Fast Group Robustness by Automatic Feature Reweighting
2309.06717 (2023-09)
Bias Amplification Enhances Minority Group Performance
and 2 more not named here
combine_and_mask 4 other papers
1 dated earlier, 3 later
2007.04612 (2020-07)
Concept Bottleneck Models
2405.04715 (2024-05)
Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning
2510.02818 (2025-10)
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
and 1 more not named here
crop_and_resize 4 other papers
1 dated earlier, 3 later
2007.04612 (2020-07)
Concept Bottleneck Models
2403.03375 (2024-03)
Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations
2510.02818 (2025-10)
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
and 1 more not named here
get_accs_for_epoch_across_batches 4 other papers
1 dated earlier, 3 later
2306.11074 (2023-06)
Simple and Fast Group Robustness by Automatic Feature Reweighting
2312.03044 (2023-12)
REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training
2510.02818 (2025-10)
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
and 1 more not named here
load_log 4 other papers
1 dated earlier, 3 later
2306.11074 (2023-06)
Simple and Fast Group Robustness by Automatic Feature Reweighting
2312.03044 (2023-12)
REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training
2510.02818 (2025-10)
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
and 1 more not named here
sanitize_df 4 other papers
1 dated earlier, 3 later
2306.11074 (2023-06)
Simple and Fast Group Robustness by Automatic Feature Reweighting
2312.03044 (2023-12)
REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training
2510.02818 (2025-10)
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative. Simplicity bias can lead to the model making biased predictions which have poor out-of-distribution (OOD) generalization. To address this, we propose a framework that encourages the model to use a more diverse set of features to make predictions. We first train a simple model, and then regularize the conditional mutual information with respect to it to obtain the final model. We demonstrate the effectiveness of this framework in various problem settings and real-world applications, showing that it effectively addresses simplicity bias and leads to more features being used, enhances OOD generalization, and improves subgroup robustness and fairness. We complement these results with theoretical analyses of the effect of the regularization and its OOD generalization properties.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.06161")
get_code_for_paper("2310.06161")
have("2310.06161")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2310.06161.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2310.06161.svg)](https://syntology.ai/paper/2310.06161)

Connect an agent — have() is free.